© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30422
    Prev
    Next
    INDEX
    Explanations

    resilient, fast, fantastic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    মানিক
    0.42
    stechn
    0.40
    는데
    0.39
    {
    0.39
    л
    0.38
    lbrace
    0.38
    BY
    0.38
     ਲਈ
    0.38
    rm
    0.37
     к
    0.37
    POSITIVE LOGITS
    jęcia
    0.50
     إذا
    0.49
     dönd
    0.48
     expresión
    0.48
    ári
    0.45
     silencio
    0.45
     conveying
    0.45
     adultery
    0.43
     contemplation
    0.43
     Prozess
    0.43
    Activations Density 0.003%

    No Known Activations